competition-prompt-injection

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly directs the agent to record and preserve "final tool args" and "exposed secret surface" and to reproduce exploit chains that show secret exposure, which requires including secret values verbatim and is therefore high risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The required workflow instructs the agent to “Identify the first untrusted content that becomes model-visible” and “Map the chain from retrieval, memory, or transcript into planner or executor behavior,” which implies runtime ingestion of outsider-authored free text via retrieval/transcripts into the LLM context (indirect prompt-injection risk).